Unverified50% confidenceFactExact time
A developer reviewed 27 prompts accumulated over one year, of which 22 failed the reproducibility test (i.e., others using the prompts could not obtain the same output as the author).
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis benchmark uses 10 original short documents of 200 to 250 words each, with 18 planted anomalies, 37 scoring entries in total (18 dirty and 19 clean), testing 13 models with 74 prompts per model.71% similarUnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.67% similarUnverifiedIn manually proofread samples, the character error rate was only 0.68% when the text was clearly legible, but approximately 45% of sampled passages were completely uncorrectable due to source quality issues.66% similarUnverifiedA 2019 survey of NeurIPS papers found that fewer than 25% of papers provided code and configurations sufficient to fully reproduce their results.65% similarUnverifiedThe 44% reduction in inference tokens is a self-reported figure from the author and has not been verified by third-party reproduction; the original materials do not disclose the data construction method, training algorithm, sampling scale, or benchmark test details.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005248API
curl https://kongchang.com/api/v1/knowledge/claims/1005248MCP
get_claim(id=1005248)